Claim Missing Document
Check
Articles

Found 5 Documents
Search

Sistem E-Customer Relationship Management Berbasis Web untuk Pengelolaan Pelanggan Nur Sabrina; Dewi Anggraeni; Akmal Nasution
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3353

Abstract

Advances in information technology are driving businesses to utilize digital systems to improve the quality of customer service. Cafe Kekynian, as a culinary business, still faces challenges in managing customer data and transactions, which were previously handled manually, making it difficult to record transaction histories and monitor customer activity. This study aims to design and implement a web-based Customer Relationship Management (CRM) system to support more effective customer relationship management. The research method employed is software engineering using the Software Development Life Cycle (SDLC) approach, which includes the stages of requirements analysis, system design, implementation, and system testing. Research data was obtained through observation, interviews, and documentation conducted at Cafe Kekynian. System testing was performed using the Black Box Testing method to ensure that every system function operates in accordance with user needs. The results of the study indicate that the developed CRM system is capable of integrating customer data management, transaction recording, and purchase history storage into a single centralized database. The implementation of this system facilitates managers in monitoring customer activities, improves the efficiency of transaction data management, and supports the formulation of more effective customer service strategies.
Pemanfaatan Artificial Intelligence (AI) dalam Dunia Pendidikan untuk Meningkatkan Kreativitas Guru SD Brainfor Islamic School Nasrun Marpaung; Akmal Nasution; Edi Kurniawan; Mardalius Mardalius
Journal Of Indonesian Social Society (JISS) Vol. 4 No. 2 (2026): JISS - Juni
Publisher : PT. Padang Tekno Corp

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59435/jiss.v4i2.723

Abstract

Perkembangan teknologi kecerdasan buatan atau Artificial Intelligence (AI) telah memberikan dampak transformasi yang masif di berbagai sektor, termasuk pendidikan. Guru dituntut untuk beradaptasi dengan alat digital guna menciptakan suasana belajar interaktif bagi siswa generasi Z dan Alpha. Pengabdian kepada Masyarakat (PkM) ini bertujuan memberikan solusi atas keterbatasan literasi digital guru di SD Brainfor Islamic School melalui pelatihan intensif pemanfaatan Generative AI. Fokus kegiatan meliputi penggunaan AI Teks (ChatGPT, Notion AI) untuk administrasi, serta AI Multimodal (Gemini AI, Canva AI, Suno AI) untuk pembuatan RPP, ilustrasi kelas, dan musik edukatif. Metode pelaksanaan menggunakan pendekatan Participatory Action Learning System (PALS) yang terdiri dari tahap sosialisasi, pelatihan hands-on, dan evaluasi. Hasil kegiatan menunjukkan lonjakan rata-rata pemahaman peserta dari 35% pada tahap pre-test menjadi 88% pada tahap post-test. Seluruh peserta berhasil menghemat 50% waktu penyusunan administrasi dan menghasilkan minimal satu produk media pembelajaran interaktif secara mandiri. Pemanfaatan AI terbukti mereduksi kebosanan belajar siswa dan sangat membantu guru berinovasi.    The development of Artificial Intelligence (AI) technology has brought massive transformation in various sectors, including education. Teachers are required to adapt to digital tools to create interactive learning environments for Generation Z and Alpha students. This Community Service (PkM) aims to provide a solution to the limited digital literacy of teachers at SD Brainfor Islamic School through intensive training on Generative AI. The focus includes the use of Text AI (ChatGPT, Notion AI) for administration, and Multimodal AI (Gemini AI, Canva AI, Suno AI) for creating lesson plans, class illustrations, and educational music. The implementation method uses the Participatory Action Learning System (PALS) approach consisting of socialization, hands-on training, and evaluation stages. The results showed a surge in participants' average understanding from 35% in the pre-test to 88% in the post-test. All participants successfully saved 50% of their administration time and independently produced at least one interactive learning media product. The use of AI is proven to reduce student boredom and greatly helps teachers innovate.
DIAGNOSIS KEBUTUHAN GIZI PADA BALITA MELALUI PENERAPAN SISTEM PAKAR MENGGUNAKAN METODE FORWARD CHAINING Silfiana Silfiana; Akmal Nasution; Sahren Sahren
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 3 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i3.6349

Abstract

Gizi adalah suatu proses organisme menggunakan makanan yang dikonsumsi secara normal melalui proses pencernaan, penyerapan, transportasi, penyimpanan, metabolisme dan pengeluaran zat-zat yang tidak digunakan untuk mempertahankan kehidupan, pertumbuhan dan fungsi normal dari organ-organ serta menghasilkan energi. Kekurangan gizi berdampak pada beberapa perubahan penting dalam sistem metabolisme tubuh, diantaranya penurunan tingkat filtrasi yang terjadi pada ginjal, gangguan pada pertahanan usus di lambung dan saluran cerna secara umum. fakta-fakta untuk diagnosis kebutuhan gizi pada balita penulis dapat dari Puskesmas Rawang Panca Arga dengan menggunakan Seperti metode penelitian yang digunakan adalah metode forward chaining disebut juga penalaran dari bawah ke atas karena penalaran dari fakta pada tingkat bawah menuju konklusi pada tingkat atas didasarkan pada fakta. Keterbatasan waktu dari dokter dan bidan menyebabkan orang tidak bisa setiap saat dan waktu untuk berkonsultasi dengan dokter dan bidan diagnosis kebutuhan gizi pada balita. Maka dari itu dalam skripsi ini penulis merancang aplikasi sistem pakar untuk mendiagnosis kebutuhan gizi pada balita. Aplikasi ini menggunakan metode forward chaining yang menelusuri fakta-fakta terkait kebutuhan gizi pada balita hingga nantinya menghasilkan diagnosis dan solusi.
ANALISIS SPASIAL KEMISKINAN DENGAN K-MEANS DAN SISTEM INFORMASI GEOGRAFIS (SIG) DI DESA PONDOK BUNGUR Akmal Nasution; Mohd. Siddik; Endra Saputra
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 8 No. 4 (2025): November 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i4.4660

Abstract

Abstract: Poverty is a complex social problem and requires a more in-depth analytical approach. To determine the level of poverty in a community, variables such as education, employment, income, ownership, housing conditions, and access to clean water and electricity are needed. Pondok Bungur is a village in Asahan Regency consisting of 10 hamlets, the majority of whose residents have low incomes, do not own secondary necessities, use water other than from the Regional Water Company (PDAM), and have limited access to electricity. Due to the lack of a clear classification of welfare, social assistance is often not well-targeted. As a solution, data science techniques with the k-means algorithm are applied to classify the level of poverty in the village. This study aims to identify which hamlets have the highest, medium, and low levels of poverty while analyzing the spatial distribution of poverty in Pondok Bungur village by integrating the k-means method and a geographic information system. The targeted outputs of this study are publications in Sinta 3-accredited journals and ready-to-use systems/applications. The results of this study are expected to provide an overview of the spatial distribution of poverty and become a basis for decision-making for the local government. The Technology Readiness Level (TKT) of this research is at level 5, where the K-Means method has been tested on real-world datasets and can be applied to spatial analysis in a broader context. The developed geographic information system will be tested for its validity in visualizing poverty data to support data-driven policymaking. Keyword: Poverty; K-Means; GIS; Clustering; Spatial Analysis. Abstrak: Kemiskinan merupakan permasalahan sosial yang kompleks dan memerlukan pendekatan analitis yang lebih mendalam. Untuk menentukan tingkat kemiskinan dalam masyarakat, diperlukan variabel-variabel seperti pendidikan, pekerjaan, penghasilan, kepemilikan, kondisi tempat tinggal, serta akses terhadap air bersih dan listrik. Pondok bungur merupakan sebuah desa di Kabupaten Asahan yang terdiri dari 10 dusun, mayoritas penduduknya berpenghasilan rendah, tidak memiliki barang kebutuhan sekunder, menggunakan air yang bukan dari PDAM, dan memiliki akses listrik yang terbatas. Karena tidak adanya klasifikasi yang jelas mengenai kesejahteraan ini akibatnya bantuan sosial sering kali tidak tepat sasaran. Sebagai solusinya, teknik data science dengan algoritma k-means diterapkan untuk mengklasifikasikan tingkat kemiskinan di desa tersebut. Penelitian ini bertujuan untuk mengidentifikasi dusun mana yang memiliki tingkat kemiskinan tertinggi, menengah, dan rendah sekaligus menganalisis distribusi spasial kemiskinan di desa pondok bungur ini dengan mengintegrasikan metode k-means dan sistem informasi geografis. Luaran yang ditargetkan dari penelitian ini berupa publikasi jurnal terakreditasi sinta 3 dan sistem/aplikasi yang siap pakai. Hasil penelitian ini diharapkan dapat memberikan gambaran distribusi spasial kemiskinan dan menjadi dasar pengambilan keputusan bagi pemerintah daerah. Tingkat Kesiapan Teknologi (TKT) penelitian ini berada pada level 5, di mana metode K- Means telah diuji dengan dataset nyata dan dapat diterapkan untuk analisis spasial dalam lingkungan yang lebih luas. Sistem informasi geografis yang dikembangkan akan diuji validitasnya dalam memvisualisasikan data kemiskinan guna mendukung pengambilan kebijakan berbasis data.  Kata kunci: Kemiskinan; K-Means; SIG; Clustering; Analisis Spasial.
Application of Stacking Ensemble Learning for Classifying Patient Revisit Patterns in Primary Healthcare Facilities Nasrun Marpaung; Dewi Maharani; Akmal Nasution
Journal of Computer Science and Technology (JOCSTEC) Vol 4 No 3 (2026): JOCSTEC - September
Publisher : PT. Padang Tekno Corp

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59435/jocstec.v4i3.947

Abstract

The increasing volume of patient visits in primary healthcare facilities (such as community health centers and clinics) demands efficient resource management and scheduling systems. The inability to predict patient arrival patterns often leads to long queues and suboptimal allocation of medical personnel. To overcome these issues, this study proposes the development of an intelligent framework based on Stacking Ensemble Learning to accurately classify and predict patient revisit frequency patterns. The proposed architecture integrates three heterogeneous base classification models (base learners), namely Logistic Regression (LR), Support Vector Machine (SVM) with non-linear Radial Basis Function (RBF) kernel projection, and Random Forest (RF). The probability predictions from these three base models are then combined into a secondary Logistic Regression based meta-learner to optimize the final decision and reduce the predictive bias of single models. Experiments were conducted using a dataset sourced from actual primary healthcare medical records, totaling 499 data entries. Given the highly imbalanced distribution of demographic data, the preprocessing stages were comprehensively designed, encompassing numerical scale feature standardization and the application of the SMOTE (Synthetic Minority Oversampling Technique) class balancing algorithm. Model testing was performed using a 5-fold stratified cross-validation scheme to ensure the robustness of the model's generalization. Comprehensive evaluation results proved that the Stacking Ensemble architecture achieved peak performance with an Accuracy of 88.4%, Precision of 85%, Recall of 90%, and an F1-Score of 0.88. Furthermore, curve analysis revealed an Area Under the Receiver Operating Characteristic (AUC-ROC) score of 0.961 and a Precision-Recall AUC of 0.95, consistently outperforming the capabilities of each individual baseline model. These findings confirm that combining hybrid machine learning models can produce highly stable and reliable predictions while minimizing false negative errors. This architecture holds massive potential for practical implementation as the foundation of a decision support system in managing operational services within primary healthcare facilities.